{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GY3VKSLRG3BB766HV4AIKSXJGF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35c9bf63d9d23496b242a341c19d1c60c197a02c6fbfee72306b9fb9ddb3508f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:43:02Z","title_canon_sha256":"151a5756e338d00852169839fc436623e6afe3011dcf2f1ee37c85b7418fcf6e"},"schema_version":"1.0","source":{"id":"2606.07687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07687","created_at":"2026-06-09T00:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07687v1","created_at":"2026-06-09T00:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07687","created_at":"2026-06-09T00:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"GY3VKSLRG3BB","created_at":"2026-06-09T00:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"GY3VKSLRG3BB766H","created_at":"2026-06-09T00:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"GY3VKSLR","created_at":"2026-06-09T00:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:ff257e794c274966a044aac8faa0360e960ffc320d3a8e73ab28ed10e104d726","target":"graph","created_at":"2026-06-09T00:04:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.07687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces. We study this question through a unified probe-based evaluation across diverse encoder families, including image-only self-supervision, video pretraining with and without latent prediction, reconstruction-based autoencoders, diffusion models, and shortcut-forcing dynamics models. Using a common inverse-dynamics probing objective, we find that action-relevant structure is driven primarily by temporal vide","authors_text":"Hanseul Kim, Jaejin Lee, Jeongjae Park, Jewon Yeom, Sungmok Jung, Taesup Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:43:02Z","title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07687","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:823bafc4c2726277e7e7b503961320f3526d9924731dcad0af2db8a5c74e10e2","target":"record","created_at":"2026-06-09T00:04:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35c9bf63d9d23496b242a341c19d1c60c197a02c6fbfee72306b9fb9ddb3508f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T04:43:02Z","title_canon_sha256":"151a5756e338d00852169839fc436623e6afe3011dcf2f1ee37c85b7418fcf6e"},"schema_version":"1.0","source":{"id":"2606.07687","kind":"arxiv","version":1}},"canonical_sha256":"363755497136c21ffbc7af00854ae9316a14a16b0279a825930715f93681e880","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"363755497136c21ffbc7af00854ae9316a14a16b0279a825930715f93681e880","first_computed_at":"2026-06-09T00:04:46.852207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:46.852207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0SN74P+5DpF0oLsDCbnU0DOWAm/L5pCVURcfTJ8C7i6dili2iBKbhznmWwvoqgb8fpKHSSITwrmwAX8xTvMBg==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:46.852570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:823bafc4c2726277e7e7b503961320f3526d9924731dcad0af2db8a5c74e10e2","sha256:ff257e794c274966a044aac8faa0360e960ffc320d3a8e73ab28ed10e104d726"],"state_sha256":"6e216dd29efc376b22732a9bf40765e2ccd975317876c3a88bccca2ad1a8c4fc"}